A National-Scale 1-km Resolution PM2.5 Estimation Model over Japan Using MAIAC AOD and a Two-Stage Random Forest Model

Abstract

Satellite-based models for estimating concentrations of particulate matter with an aerodynamic diameter less than 2.5 μm (PM2.5) have seldom been developed in islands with complex topography over the monsoon area, where the transport of PM2.5 is influenced by both the synoptic-scale winds and local-scale circulations compared with the continental regions. We validated Multi-Angle Implementation of Atmospheric Correction (MAIAC) aerosol optical depth (AOD) with ground observations in Japan and developed a 1-km-resolution national-scale model between 2011 and 2016 to estimate daily PM2.5 concentrations. A two-stage random forest model integrating MAIAC AOD with meteorological variables and land use data was applied to develop the model. The first-stage random forest model was used to impute the missing AOD values. The second-stage random forest model was then utilised to estimate ground PM2.5 concentrations. Ten-fold cross-validation was performed to evaluate the model performance. There was good consistency between MAIAC AOD and ground truth in Japan (correlation coefficient = 0.82 and 74.62% of data falling within the expected error). For model training, the model showed a training coefficient of determination (R2) of 0.98 and a root mean square error (RMSE) of 1.22 μg/m3. For the 10-fold cross-validation, the cross-validation R2 and RMSE of the model were 0.86 and 3.02 μg/m3, respectively. A subsite validation was used to validate the model at the grids overlapping with the AERONET sites, and the model performance was excellent at these sites with a validation R2 (RMSE) of 0.94 (1.78 μg/m3). Additionally, the model performance increased as increased AOD coverage. The top-ten important predictors for estimating ground PM2.5 concentrations were day of the year, temperature, AOD, relative humidity, 10-m-height zonal wind, 10-m-height meridional wind, boundary layer height, precipitation, surface pressure, and population density. MAIAC AOD showed high retrieval accuracy in Japan. The performance of the satellite-based model was excellent, which showed that PM2.5 estimates derived from the model were reliable and accurate. These estimates can be used to assess both the short-term and long-term effects of PM2.5 on health outcomes in epidemiological studies.

Interpolation-Based Fusion of Sentinel-5P, SRTM, and Regulatory-Grade Ground Stations Data for Producing Spatially Continuous Maps of PM2.5 Concentrations Nationwide over Thailand

“…The dataset was split into two parts, out of which approximately 10% (6 out of 63 stations) was used as a testing set, by randomly extracting one station from northern, northeastern, eastern, and southern regions, and two stations from central regions based on their uneven spatial distribution. The remaining data corresponding to 90% (57 stations) was used as a training set, while the split was randomly implemented 10 times for 10-fold cross-validation [64][65][66] to exclude the impact of extreme values in each division, especially in the case of adopting data with large variance.…”

Data level and decision level fusion of satellite multi-sensor AOD retrievals for improving PM2.5 estimations, a study on Tehran

“…In addition to the SVR, decision trees have shown a high ability to solve nonlinear regression problems. Advanced versions of decision trees, such as random forest (RF), have been used in many studies to estimate PM2.5 concentrations from AOD data Jung et al [2021]; Kianian et al [2021]; . RF is partially resistant to over-fitting by generating an ensemble of Fig.…”

“…So far, several methods have been used to determine the relationship between PM2.5 and AOD. Some of these methods are based on machine learning, which has proven their capability in numerous studies ; ; ; ; Jung, Chen, and Nakayama [2021]; Kianian, Liu, and Chang [2021]; ; Ni et al [2018]; ; Yang et al [2019]; You et al [2016]; Zhao et al [2020] Zhao et al [2020] Yang et al [2019] Bagheri [2022]. The various algorithms used in previous studies indicate the importance of algorithm selection for modeling the PM2.5-AOD relationship.…”

PM2.5 Modeling and Historical Reconstruction over the Continental USA Utilizing GOES-16 AOD

“…There have been studies that have explored machine learning methods for PM 2.5 modeling. Tree-based methods, deep networks, and the combination of traditional machine learning methods with ancillary data were found to be effective methods in PM 2.5 modeling [22,29,[31][32][33][34][35]. Statistical methods and physical or chemical theories based methods were also found capable in PM 2.5 modeling, such as the urban fine scale PM 2.5 estimation by using Landsat 8 images [36], Gaussian processes modeling in a Bayesian hierarchical setting [10], long-term estimation using remote sensing products and chemical transport models [37], and the estimating of PM 2.5 using a hybrid method that combines multiple sub-models [38].…”